An apparatus for generating a three-dimensional model of an object includes a storage unit that stores three-dimensional coordinates of plural vertices on a standard model of the object, an image input unit that inputs plural input images acquired by photographing the object, a first detection unit that detects a coordinate of a first point corresponding to a vertex on the standard model, from a first image selected from among the plural input images, a second detection unit that detects a coordinate of a second point corresponding to the coordinate of the first point, from a second image other than the first image, a depth computation unit that computes a depth of the first point by using the coordinates of the first and second points, and a first update unit that updates the three-dimensional coordinate on the standard model based on the coordinate of the first point and the calculated depth.
Legal claims defining the scope of protection, as filed with the USPTO.
1. An apparatus for generating a three-dimensional model of an object, comprising: a storage unit that stores three-dimensional coordinates (X,Y,Z) of a plurality of vertices on a standard model of the object; an image input unit that inputs a plurality of input images acquired by photographing the object; a first detection unit that detects a coordinate (x,y) of a first point corresponding to a vertex on the standard model, from a first image selected from among the plurality of input images; a second detection unit that detects a coordinate (x′,y′) of a second point corresponding to the coordinate of the first point on the first image, from a second image other than the first image, input by the image input unit; a depth computation unit that computes a depth of the first point on the first image by using the coordinate (x,y) of the first point on the first image and the coordinate (x′,y′) of the second point on the second image; and a first update unit that updates the three-dimensional coordinate (X,Y,Z) on the standard model based on the coordinate (x,y) of the first point on the first image and the depth calculated by the depth computation unit, wherein the first detection unit includes an interpolation unit that computes the coordinate (x,y) of the first point on the first image by interpolation using coordinates (x″,y″) of third points on the first image corresponding to predetermined vertices on the standard model and using three-dimensional coordinates (X′,Y′,Z′) of the predetermined vertices on the standard model.
2. The apparatus according to claim 1 , wherein the depth computation unit computes the depth of the first point on the first image in accordance with a stereo method using the coordinate (x,y) of the first point on the first image and the coordinate (x′,y′) of the second point on the second image.
3. The apparatus according to claim 1 , wherein the first detection unit includes: an inclination computation unit that computes a difference of inclinations between the standard model and the object included in the first image by using coordinates (x″,y″) of third points on the first image corresponding to predetermined vertices on the standard model and using three-dimensional coordinates (X′,Y′,Z′) of the predetermined vertices on the standard model; a second updating unit that updates three-dimensional coordinates of the standard model, based on the difference of the inclinations, such that the difference of the inclinations of the standard model is smaller than a threshold; and an interpolation unit that calculates the coordinate (x,y) of the first point on the first image by interpolation using the coordinates (x″,y″) of the third points on the first image corresponding to the predetermined vertices on the standard model and using the three-dimensional coordinates (X″,Y∴,Z″) of the predetermined vertices on the updated standard model.
4. A method for generating a three-dimensional model of an object, comprising: an image input step of inputting a plurality of input images acquired by photographing the object; a first detection step of detecting a coordinate (x,y) of a first point corresponding to a vertex on a standard model, from a first image selected from among the plurality of input images; a second detection step of detecting a coordinate (x′,y′) of a second point corresponding to the coordinate of the first point on the first image, from a second image other than the first image, input in the image input step; a depth computation step of computing a depth of the first point on the first image by using the coordinate (x,y) of the first point on the first image and the coordinate (x′,y′) of the second point on the second image; and a first update step of updating the three-dimensional coordinate (X,Y,Z) of the standard model based on the coordinate (x,y) of the first point on the first image and the depth calculated in the depth computation step, an interpolation step of computing the coordinate (x,y) of the first point on the first image by interpolation using coordinates (x″,y″) of third points on the first image corresponding to predetermined vertices on the standard model and using three-dimensional coordinates (X′,Y′,Z) of the predetermined vertices on the standard model.
5. The three-dimensional model generating method according to claim 4 , wherein the depth computation step is for computing the depth of the first point on the first image in accordance with a stereo method using the coordinate (x,y) of the first point on the first image and the coordinate (x′,y′) of the second point on the second image.
6. A computer readable medium storing a program to make a computer perform generating a three-dimensional model of an object, the program comprising: an image input step of inputting a plurality of input images acquired by photographing the object; a first detection step of detecting a coordinate (x,y) of a first point corresponding to a vertex on a standard model, from a first image selected from among the plurality of input images; a second detection step of detecting a coordinate (x′,y′) of a second point corresponding to the coordinate of the first point on the first image, from a second image other than the first image, input in the image input step; a depth computation step of computes a depth of the first point on the first image by using the coordinate (x,y) of the first point on the first image and the coordinate (x′,y′) of the second point on the second image; and an update step of updating the three-dimensional coordinate (X,Y,Z) of the standard model on based on the coordinates (x,y) of the first point on the first image and the depth calculated in the depth computation step, wherein the first detection step includes: an interpolation step of computing the coordinate (x,y) of the first point on the first image by interpolation using coordinates (x″,y″) of third points on the first image corresponding to predetermined vertices on the standard model and using three-dimensional coordinates (X′,Y′,Z′) of the predetermined vertices on the standard model.
7. The storage medium according to claim 6 , wherein the depth computation step is for computing the depth of the first point on the first image in accordance with a stereo method using the coordinate (x,y) of the first point on the first image and the coordinate (x′,y′) of the second point on the second image.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
March 6, 2006
April 27, 2010
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.